VoiScribe

Inspiration

Communication is so important in today's world. Therefore, it is unfair that it may not be accessible to some parts of the population. We wanted to provide an easy solution in order to empower these individuals and build an inclusive environment.

What it does and how we built it

We used the Symphonic Lab’s voiceless API in order to interpret lip syncing movements into text/transcripts for people with speech impairments, which can be visualized on an application like google meet through closed captions. Once transcribed, we used google translate’s text-to-speech function to convert that text into speech, so that others can hear the intended words.

Challenges we ran into

We ran into a couple of challenges when developing the project. Firstly, there were bugs in the Symphonic API which slowed down our progress. However, we were able to overcome this challenge, with the help of our wonderful mentors, and create a working prototype.

Accomplishments that we're proud of

Despite multiple technical errors, we persevered through our project and successfully came up with an MVP. We collaborated effectively under time constraints and integrated feedback from mentors to constantly improve the code.

What we learned

We took so much away from this experience. Learning the tech was definitely one aspect of it, but in the process we developed other real-world skills such as critical thinking, problem-solving, building user-centric design, collaborating and so much more!

What's next for VoiScribe

In the future, we plan to make it capable of processing live feed. We also plan to we plan to incorporate a sign language predictor that can detect sign language when lip-sync to speech fails. Lastly, we plan to make it a chrome extension so that it is easily accessible to the public!